AI Agents Crash Course: Build with Python & OpenAI
A four-hour, hands-on course that builds a complete AI nutrition-assistant agent with OpenAI's Agents SDK, covering tool calling, retrieval-augmented generation, the Model Context Protocol, multi-agent orchestration, memory, guardrails and cloud deployment.
This course takes a learner from a first OpenAI agent to a deployed, production-style agent over four hours of material, delivered as forkable exercises intended to be run in a GitHub Codespace. The first hour covers building and debugging a first agent and calling external APIs through tool calling; the second covers retrieval-augmented generation for contextual knowledge and the Model Context Protocol; the third covers multi-agent orchestration, memory, prompt engineering and guardrails for safe behavior; and the fourth covers building a production-style chatbot and deploying it to the cloud with authentication.
The worked example throughout is a nutrition assistant that combines natural-language understanding, external API calls, retrieval, conversational memory and guardrails, deployed with cloud authentication by the end of the course. It assumes basic Python knowledge of functions, loops and object-oriented programming, and an OpenAI API key.
It is distributed as Jupyter notebooks and course materials.